aisa-twitter-command-center

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (medium risk: 0.30). The skill monitors X/Twitter feeds, search results, replies, and user profiles via the AIsa API relay, allowing any outsider to publish free text that the agent ingests at runtime.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.70). The skill makes runtime API requests to api.aisa.one, which is an uncontrolled third-party proprietary relay rather than an official publisher channel for Twitter or the agent framework, representing an unknown/unverified operational dependency.